Sat, Nov 9, 11:32 PM CST

Renderosity Forums / Poser - OFFICIAL



Welcome to the Poser - OFFICIAL Forum

Forum Coordinators: RedPhantom

Poser - OFFICIAL F.A.Q (Last Updated: 2024 Nov 09 11:21 pm)



Subject: Steven Spielberg comments about creating movies with VR actors


XENOPHONZ ( ) posted Mon, 20 June 2005 at 12:35 PM · edited Fri, 08 November 2024 at 4:19 PM

Attached Link: http://www.msnbc.msn.com/id/8271977/site/newsweek

Here's another propagation of a Drudge link.

There are images in "War of the Worlds" that are truly stunning. Is there something you're dying to get on film that isn't technologically possible yet?
What can't be donebut will be possible within five to seven yearsis to create a fully digital human being that would interface with other human beings and would be undetectable. You will not be able to tell the actor from the digital actor. Now, that terrifies me. It crosses a moral boundary to me. In the very near future, a young filmmaker will sit on his laptop and make an entire movie without having to speak to anyone. Yes, that's an art form, and there's nothing wrong with that, but there's a point where you ask, are we [filmmakers] going to become recluses who want to make movies without human contact? Collaboration is what makes being a director an electrifying experience.

So -- Mr. Spielberg has concluded that, in 5-7 years time, "a young filmmaker" will be able to create an entire movie on a laptop. No real human actors need be involved.

I'm not so sure that it'll happen as soon as 7 years away. But stranger things have occured.

I wonder if Poser will be along for the ride?

Just imagine -- the galleries filled with links to 1.5 hour long movies -- all created by us.

I don't know whether to feel extremely good or to shudder at the thought. Or both.......probably both.


No, we needn't be concerned about a "Make Art" button. Just a "Lights/Camera/Action!" button.

Automated movies. Wonderful.

Message edited on: 06/20/2005 12:37

Something To Do At 3:00AM 



dlk30341 ( ) posted Mon, 20 June 2005 at 1:01 PM · edited Mon, 20 June 2005 at 1:02 PM

On a more positve note IMHO...it would bring the Hollywood actors/actresses back down to reality & off their God like complexes. Oh, I'd love to see the day when one can turn the news on and hear nothing about who is dating who...blah...blah ...blah.....who freakin cares about this crap anyway.

I find 5-7 years a stretch as well, since even in movies like Toy Story/Shrek/any animated film, they still require real human vocals. Should be interesting nonetheless.

Message edited on: 06/20/2005 13:02


Bobasaur ( ) posted Mon, 20 June 2005 at 1:12 PM · edited Mon, 20 June 2005 at 1:14 PM

I can see people using virtual characters for some projects but not for full length movies. It's one heck heck heck of a lot of work to do it. Few (if any) individuals would be able to pull off a full 90 minute piece by themselves. Final Fantasy was cool in its own way but it required a lot of people.

I've got a few shorts I'd love to do integrating live action with virtual but real life keeps getting in the way.

I suspect that my wife would handle it better if she saw me kissing a "virtual" version of her than if she saw me kissing a real actress portraying her when I do my "How To Find And Marry Your One True Love" movie.

Even Vicky couldn't save me if I chose to depict the kinky sex.. I mean that most sacred and blessed marital union that is offered by a loving and benevolent God to legally married husbands and wives in order to fullfill the commandment: "Be fruitful and multiply!" Not that I would of course.

I hope I said that right.

[grin]

Message edited on: 06/20/2005 13:14

Before they made me they broke the mold!
http://home.roadrunner.com/~kflach/


DCArt ( ) posted Mon, 20 June 2005 at 1:14 PM

The first term was a lot easier to say! ROFL



maxxxmodelz ( ) posted Mon, 20 June 2005 at 1:17 PM

"I'm not so sure that it'll happen as soon as 7 years away. But stranger things have occured." That sounds consistent with reports I've heard from different sources. I believe nVidia projected the same within the next 10 years. Will Poser and other such apps get it by then? Possible, but unlikely, considering the rate of growth and financial benefits to all sides. Most likely, the "high end" market will see it first, then it will cycle down to the mid-range and lower-end portions of the community later on. Just a guess, but the technology will probably be very expensive to the average consumer when it first hits. For example, if you wanted to do battle scenes using the same cutting-edge software technology created for Peter Jackson's FX teams on LOTR movies, you can get it... but it will cost you $18,000 for a license, and $4000 a year for support. ;-)


Tools :  3dsmax 2015, Daz Studio 4.6, PoserPro 2012, Blender v2.74

System: Pentium QuadCore i7, under Win 8, GeForce GTX 780 / 2GB GPU.


dlk30341 ( ) posted Mon, 20 June 2005 at 1:20 PM

Didn't I hear at 1 point that Toy Story took 2 1/2 years to do???? That said, I'm sure the times to develop such movies has decreased dramatically. In addition, we'd all have to have super computers with HUGE render farms....unless technology changes dramatically over the enxt few years. LOL @ Bobasaur


maxxxmodelz ( ) posted Mon, 20 June 2005 at 1:31 PM

"Didn't I hear at 1 point that Toy Story took 2 1/2 years to do???? That said, I'm sure the times to develop such movies has decreased dramatically." I don't know how long ToyStory took exactly, but that movie was made like 10 years ago. So 10 years from now, we're talking a 20 year difference in technology development, so yeah... those rendertimes, etc. are/will be obsolete. nVidia said something like another 10 years for real-time photorealism, so a full-length movie rendered in real-time would only take a couple hours to render. ;-) Even the fastest render engines out there today, still require a relatively long time to render photorealism at film resolutions, and only recently has true GI/HDRI become viable for animation rendering. GI is still 'faked' most of the time for movies, because faking it is still much faster than running true GI calculations over the course of tens of thousands of frames, so it saves time and money.


Tools :  3dsmax 2015, Daz Studio 4.6, PoserPro 2012, Blender v2.74

System: Pentium QuadCore i7, under Win 8, GeForce GTX 780 / 2GB GPU.


jjsemp ( ) posted Mon, 20 June 2005 at 1:36 PM

I think Spielberg's dead on target. In five to seven years a young filmaker will certainly be able to create "Toy Story" or "Jimmy Neutron", both of which were Academy Award nominees, on a laptop. Ultimately it's not about the technology -- it's about the story. We lose track of that in forums like this one where everybody obsesses over finicky things like "Ambient Occlusion" or "lacrimals". You don't need Appollo Maximus or better to tell a great story. Woody (from "Toy Story") will do just fine. -jjsemp


dlk30341 ( ) posted Mon, 20 June 2005 at 1:37 PM

Technology is a wonderful thing...the changes are fascinating...keeps us all on our toes :)


dlk30341 ( ) posted Mon, 20 June 2005 at 1:39 PM

Good point jjsemp...look at the simplicity in characters in South Park....spheres/squares/triangles. I'll add, I don't care for this toon myself. But is still VERY popular.


mateo_sancarlos ( ) posted Mon, 20 June 2005 at 1:43 PM

Spielberg is wrong. A young filmmaker who never leaves his room, and who has little useful experience interacting with live human beings, can't create a character with a personality even remotely realistic. It's the same with writing novels or screenplays. The person who attempts it has to experience life in great detail, or his/her stuff will just be a fake, derivative facsimile of some movie he saw, or some book he read.


ScottA ( ) posted Mon, 20 June 2005 at 1:51 PM

Spielberg isn't really a technical guy. He's old fashioned and lets other people handle the technical work. He really doesn't know what he's talking about. George Lucas would have a much better understanding of the task. In 5-10 years we will all be switching to hardware based CG graphics cards to do the HDRI rendering. And it will make it easier to render realistic environments. But it will still take hundreds of computers and several professionals to make an all animated movie. My own best guess is that it will take anywhere between 30-50yrs. before hobbyists like ourselves will have the tools to make a Hollywood quality movie ourselves at home. Even that's being optimistic. We will see a boom in short animated films over the next 10 years. By smaller studios like Blurr studios. But not full blown Hollywood productions by home users. That's wishful thinking. And being unfamiliar with the scope of the obsticles that need to be solved first. -ScottA


cyberscape ( ) posted Mon, 20 June 2005 at 2:21 PM

I tend to agree/disagree with Spielburg. For one, he's been making movies for what... almost 30 years? Not to mention working with some of the best FX teams in the world (ILM, Stan Winston, etc). I'd say it's safe to bet that he's seen technology right now that very few of us here have been fortunate enough to even hear about. On the other hand, 5-7 years is a little too soon for predicting that any hobbyist can make thier own "actorless" full-length movie. Sure, the computing power might be available by then but, like maxxmodels said... it'll be quite expensive for most of us regular folk. Lee

------------------------------------------------------------------------------------------------------------- 

AMD FX-9590 4.7ghz 8-core, 32gb of RAM, Win7 64bit, nVidia GeForce GTX 760

PoserPro2012, Photoshop CS4 and Magix Music Maker

--------------------------------------------------------------

...and when the day is dawning...I have to say goodbye...a last look back into...your broken eyes.


XENOPHONZ ( ) posted Mon, 20 June 2005 at 2:28 PM

Frankly, I wouldn't care to make any hard and fast predictions either way.

While I understand the technical difficulties involved in producing true photorealism for a 90 minute movie.......and I seriously doubt that we'll see that for home PC's in 7 years........

.........I also realize that PC technology is increasing by leaps and bounds. It really wasn't all that long ago when a 350 mB hard drive was a huge hard drive. And 4 megs of RAM was a lot of RAM -- not to mention very expensive.

The more that technology advances, the faster that the rate of advancement accelerates.

Maybe. We'll see.

Something To Do At 3:00AM 



xoconostle ( ) posted Mon, 20 June 2005 at 2:28 PM

I can see how truly undetectable artificial humans would do nicely for storyboarding and animatics, but it will be a long time before such a capability would be more cost effective than using an actor. There are so many subtle variables involved in good acting, and just as many on the perceptive/audience end ... this isn't something that algorithms will do "better" or with the same lack of predictability as a talented human any time soon. So ultimately, the creative question is "why WOULD you want to replace humans?" If it's only to save money, that will take time. If it's to avoid human interaction ... (see mateo_sancarlos' points.) Spielberg is the first to admit to his "gee whiz" sense of wonder when it comes to high tech, but as with a lot of us, it sometimes occludes real world considerations. As with any technological innovation in the arts, advanced realism should be seen as a means to an end, not an end in itself. Defining the ends should be fun. (Heh heh ... he said "occludes" ... heh heh)


maclean ( ) posted Mon, 20 June 2005 at 2:47 PM

'There are so many subtle variables involved in good acting' Yep. The main one being unpredictablity. You can give the same lines to 10 actors and they'll all do them differently, and there will be variations according to their mood when they say the lines. It's called 'the human factor' and it's the one thing computers don't have. As for why you'd want to replace humans, here's a brief scene (from memory) from The Producers by Mel Brooks. ------------------------------- Zero Mostel : 'What else can we do? Blow up the theater? Shoot the actors?' Gene Wilder : 'Shoot the actors?? You can't shoot the actors! Actors are human beings too, you know' Zero Mostel : 'Oh yeah? Have you ever had lunch with one?' ------------------------------- mac


ziggie ( ) posted Mon, 20 June 2005 at 2:49 PM

"... a young filmmaker will sit on his laptop ..." and as a result break the darn thing, so that he will never get his movie made :-(

"You don't have to be mad to use Poser... but it helps"


Bobasaur ( ) posted Mon, 20 June 2005 at 3:10 PM

I admit i sometimes find myself envying my film director friends who can get more scenes shot over a weekend with a far larger cast than I could ever think of. I have more control but that doesn't always make it better. I'd love to have a Director of Photography. A lighting Director. A Set Designer. A Costume Designer. A Prop Master. Heck, I'd even love to have craft services. I'd rather be an animator but my productions would be better if I had a full team rather than just me. A full movie is a lot of work! I suspect Speilberg knows that but is simply focused on the technology in this quote.

Before they made me they broke the mold!
http://home.roadrunner.com/~kflach/


wolf359 ( ) posted Mon, 20 June 2005 at 3:13 PM

The original toy story took a little over two years render time ( not including post production) using a render farm of several hundred specially configured SUN Enterprise Computers with 32 GIGS of ram each . had toy story been rendered on one machine loaded with the most powerful CPU in the world at that time ,the render time would have still been over 256 years. The late Square pictures had over 1000 top end silicon graphics workstations and rendered in layered passes for light ,shadows, specular, and so on, and "Final Fantasy TSW" still took years just to render not counting post work. To suggest that people will be doing Full photorealistic CG films like FFTSW on their laptop PC;s in the next five years is wishful thinking at best . Sorry.



My website

YouTube Channel



gagnonrich ( ) posted Mon, 20 June 2005 at 3:18 PM

"it would bring the Hollywood actors/actresses back down to reality & off their God like complexes." Actually, there's already something that can do that--it's called starving actors. For every $20 million dollar performer, there's thousands of actors every bit as talented, but just haven't gotten that big break. Just about every big-name actor started as an unknown. Until they land in a blockbuster movie, it's not likely that they'll ever be fully discovered. Even then, it's takes more to be a celebrity than being a good actor. Arnold Schwarzenegger was a big movie star, but it's not hard to name dozens of better actors that were never paid as much for a movie. Then, there are pseudo-celebrities, like Paris Hilton, that haven't really done anything to be famous, but the tabloids can sell their rags by putting their photo on the cover with some scandalous headline. Celebrities will be out of the news when people stop being interested in their lives and that won't happen for a long time. There are alternatives to attention starved, media hungry celebrities, but there aren't enough people interested in those alternatives to matter. I'm not worried about actors being replaced by computers any more than I ever was about animation replacing human beings, be it traditional 2D animation or done by computers. The best animators are actors. Bugs Bunny is as real as most actors. No matter how good computers get at animating realistic figures, it'll still be easier to use a real human being because it takes less time to do it.

My visual indexes of Poser content are at http://www.sharecg.com/pf/rgagnon


maxxxmodelz ( ) posted Mon, 20 June 2005 at 3:33 PM · edited Mon, 20 June 2005 at 3:37 PM

" had toy story been rendered on one machine loaded with the most powerful CPU in the world at that time ,the render time would have still been over 256 years."

Well, it's not just the advancement of horsepower that would make the difference, but raytracing and render technology has advanced quite dramatically since TS 1 as well, and it continues to.

Back then, GI calculations would have been unheard of for use in actual production work, but today, it's possible to some extent, with advanced render algorithms like photon mapping, etc. Even as recently as a few years ago, even the pros were saying GI was unusable in production, when suddenly renderers like Brazil and Vray proved that it was possible.

A full-length feature film that is convincing enough to pull off CG character(s) without the audience even knowing would definitely require a massive collaborative effort, even if real-time photoreal rendering were a reality right now, but I think Spielberg is speaking in theoretical terms. Obviously, there's so much that goes into a full movie, one person could never accomplish it to the level of total believability by themselves, if just because of the work involved in the modeling and animation portion itself. Message edited on: 06/20/2005 15:37


Tools :  3dsmax 2015, Daz Studio 4.6, PoserPro 2012, Blender v2.74

System: Pentium QuadCore i7, under Win 8, GeForce GTX 780 / 2GB GPU.


fls13 ( ) posted Mon, 20 June 2005 at 3:37 PM

Whatever the cutting edge is, Hollywood will have it well before the regular person. That's because cutting edge cuts deep into the wallet, and their's are deeper than ours. But if you look at great stuff being done by individuals today and compare it with what studios were doing a few years ago, the garage guys are measuring up well.


maxxxmodelz ( ) posted Mon, 20 June 2005 at 3:44 PM

"But if you look at great stuff being done by individuals today and compare it with what studios were doing a few years ago, the garage guys are measuring up well." Exactly. Liam Kemp's work on "This Wonderful Life" is a good example. Not a full-length feature, obviously, but still a great CG short. He started it in 2001, completed it in 2003. Considering even more advances have occured since then which may have aided his efforts, it's still a reasonable time frame for such a work, done by an individual from the modeling stage to final render. He's currently working on his second, titled "The Normals". Can't wait to see it. :-)


Tools :  3dsmax 2015, Daz Studio 4.6, PoserPro 2012, Blender v2.74

System: Pentium QuadCore i7, under Win 8, GeForce GTX 780 / 2GB GPU.


SamTherapy ( ) posted Mon, 20 June 2005 at 3:52 PM

I think somewhere between Speilberg's predictions and wolf359's conservative view is the most likely - in terms of hardware, at least. A rule of thumb is that computers double in power and capacity while halving in price every year. So, if you take a "base" model of 1GB RAM, 200 GB HD and a 2GHz processor. Add in the currently most widely used 32 bit architecture (which, admittedly doesn't double year on year) and you can see what could happen in 10 years. You could end up with something that could wipe the floor clean with a Cray 2, but the size and cost of a packet of cigarettes. Maybe. :) The virtual actor bit, well that may not be so bad. How about a 3D model with the same physical presence as Arnie, for example, but with the acting ability of Lawrence Olivier? As for the nuances of the performance, that would be down to the director. Directors would need to learn new skills, tweaking the virtual performance (and maybe adding in a random element here or there) to get the best possible version out on screen.

Coppula eam se non posit acceptera jocularum.

My Store

My Gallery


Keith ( ) posted Mon, 20 June 2005 at 4:01 PM

*'There are so many subtle variables involved in good acting'

Yep. The main one being unpredictablity. You can give the same lines to 10 actors and they'll all do them differently, and there will be variations according to their mood when they say the lines.*

It's not just that.

If you ever watched "Who's Line is it Anyway?" there's a bit they do frequently where two or three of the comedians improv a scene, usually fairly straight, and then the fourth (usually Colin Mochrie) runs in acting as a director and tells them to do the same scene another way: as drunken ninjas or something.

Now that's done for comedy but it's only a takeoff on what directors really do. "Give me a little more intensity", "Act more betrayed", "Show that you realize what's happening a little sooner in the conversation". It's easy with human actors.

For CG, now, you have to view the scene, go back to the animators with the changes you want, they spend hours or days changing it, view the scene again, go back the animators if you want it tweaked some more...and that isn't going to change until you have an AI that can understand what the director means and make the changes quickly.

Even what's considered the current pinnacle of CG characters, Gollum, depended heavily on Andy Sirkis for physical and voice acting. Gollum could cower because the guy in the suit with the reflective tape cowered in a way that everyone instantly recognized as cowering.

Now, this isn't to say it's impossible. There's some damn fine CG out there with expressive characters who rely purely on the animation. But it's a lot slower than directing a human.



fls13 ( ) posted Mon, 20 June 2005 at 4:40 PM

http://www.panicstruckpro.com/revelations/revelations.html The effects in this one are pretty amazing, although it's not a one man effort to be sure. :O)


Argon18 ( ) posted Mon, 20 June 2005 at 5:46 PM

Well the thing about CGI movies like Toy Story, Shrek, Finding Nemo and Shark Tales is that you can have characters and situations impossible with regular actors. That's an advantage that's going to improve with greater technology But the getting the emotional depth of the performance for the voices without an actor doing them is problematic, how far are they along with voice synthesizers and AI to direct them? That kind of technology isn't going to get that cheap and that easy in less than a decade. I agree that like with movies like Sin City, physical location shooting will be less critcal and the animating of the characters will improve so you can't tell the difference like some the ones in Revenge of the Sith, but you'll still need to talk to people to get the story told with the kind of performance that's believable. Orson Welles made people believe War of the Worlds with just voices on the radio, but if you didn't have actors to perform the voices like Eddie Murphy did with Donkey in Shrek, Robin Williams did with the Genie in Aladdin and Robert DeNiro did with Don Leno in Shark Tales, then those characters wouldn't have gone over like they did and been believable.


Click to get a printed and bound copy plus T-shirts, mugs and hats


jjsemp ( ) posted Mon, 20 June 2005 at 6:50 PM

George Lucas would have a much better understanding of the task.<< ScottA, You're right, he does. And he'd be the first to disagree with you. About eight years ago I sat in Lucas' office and personally listened to him discuss the blistering pace of computer graphics. He spoke of how he watched image "morphing" technology basically get invented at ILM and in the short space of two years go from hi-end movies like "Terminator 2" to everybody's PC desktop. He'd be the first to predict (and already has several times) that very soon now, actors will be completely replaced by CGI. So he'd respectfully disagree with you about Spielberg's prediction. He'd think Spielberg is right (and so do I). >>My own best guess is that it will take anywhere between 30-50yrs. before hobbyists like ourselves will have the tools to make a Hollywood quality movie ourselves at home. Even that's being optimistic.<< Wolf359, All you have to do is look at the demos for the new Sony Playstation 2 (specifically the Alfred Molina-as-"Doc Oc" demo) to realize that your prediction is way, way off. Realistic CGI characters on game machines is just about here. Realistic CGI characters on home PCs is right around the corner by even the most conservative estimate. Heck, in 30 to 50 years we'll probably all be jacking directly into our cerebral cortexes for truly immersive 3D experiences, a la William Gibson's "Neuromancer!" >>Well the thing about CGI movies like Toy Story, Shrek, Finding Nemo and Shark Tales is that you can have characters and situations impossible with regular actors.<< I agree here with Argon18. Most CGI movies don't even need photorealism. Spielberg's simply said that making a movie would be possible on a laptop, not that it would need to look absolutely real. And, yes, you'll still need actors for voices. >>Spielberg is wrong. A young filmmaker who never leaves his room, and who has little useful experience interacting with live human beings, can't create a character with a personality even remotely realistic.<< All kinds of remote, hermetic, anti-social people have written unforgettable characters in books. Take Robert E. Howard (Conan the Barbarian), H.P. Lovecraft (the Chthulhu Mythos) or Margaret Mitchell (Gone With the Wind) just to name a few. These authors were notorious for never leaving the house and being very anti-social. In theory, a young filmaker who doesn't leave his room can tell a story just as well as they could -- especially since now a hermetic young mind has the internet and TV with which to view the world-at-large. -jjsemp


fls13 ( ) posted Mon, 20 June 2005 at 7:02 PM

http://www.vfxworld.com/?atype=articles&id=2527


ScottA ( ) posted Mon, 20 June 2005 at 8:46 PM

I have some swamp land in Arizona for sale cheap if you're interested. ;-)


Fazzel ( ) posted Mon, 20 June 2005 at 9:06 PM

I have some swamp land in Arizona for sale cheap if you're interested. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ They are called cienagas in Arizona.



danamongden ( ) posted Mon, 20 June 2005 at 11:13 PM

I think sound may turn out to be the real problem to "actorless" movies. Forget about conveying dramatic emotions, most text-to-speech solutions are doing well to be understood. I've heard some of the really high-end ones, and they're better, but they're still a far cry from sounding truly human. I know someone who does a lot of speech-driven voice-mail menus, and the ironic thing is that while they're getting better at understanding speech, the speech that the computer plays to the customer is all recorded from real humans. Beyond that, I think about all the foley artists, they guys who make all the sound effects, from dripping water to Earth-shattering Kabooms. While technically not actors, they do most of their work by recording real objects and putting them through trial-and-error modifications to get something that just sounds right. For the young filmmaker to crank something out in his basement, he'd need to solve these sound issues. The reason this seems to be a limiting factor to me is that I haven't seen much work done in this area. I first thought about the issue back in 92 or 93 when playing with an early version of 3D Studio. While we've spent a couple of decades and millions of research dollars working out the way light interacts with a variety of environments, I haven't seen much effort put into sound. For example, what is the sound of someone walking across the floor? Well, what kind of shoes? What kind of floor? Is it carpeted? What kind of carpet? How thick? What material? How heavy is the step? What material is on the walls and ceiling? How far away are the walls and ceiling? Where is the microphone relative to the steps? Are there any other sound sources in the room? We deal with a lot of the same issues in graphics rendering, but with light. Where's "Poser for Sound"? It doesn't exist, not even version 1. Maybe there's an active community involved in this research, but I've missed it. And each year that I go to SIGGRAPH, I look for presentations on this kind of thing. Admittedly, it's a graphics, not sound, conference, but there is a lot of animation there, and they have to deal with sound issues all the time. And yet, the closest thing I've seen was something that allowed you to move various sound sources (instruments in a string quartet) to be moved around a virtual room and then balance that sound between eight speakers spread through the real-world room. When I later asked one of the presenters how his software would deal with a change in the type of wall surfacing, say switching from cloth to marble, he just got this blank face and said, "We don't deal with those kinds of problems." Plus, the human ear is very discriminating. We think of it as a low-bandwidth sense because sound compresses so much tighter than video, but studies show that our visual processing is all about throwing away visual information to grab only key details, i.e. edges, motion, specific colors, etc. Maybe our hearing is similar in that respect, but I think about the innate ability to pick out a mistuned note in a chord structure, and I realize that we've got some powerful audio processing in our heads. Now, I'm no sound expert, but I think this is going to be a tough problem, and to my knowledge, it's not being attacked aggressively.


pdxjims ( ) posted Tue, 21 June 2005 at 7:56 AM

First, we're talking about a number of things involved. Currently, someone using only Poser could create a movie with a very realistic feel to it. It'd take time, organization, and a number of machines and people, but it could be done. The technolgy is already available, just look at some of the portraits in the gallery here. Second, the things that will make it really feasable are faster machines and better software. Software needs to be made to allow for direction, the same way a live director can instruct real actors. Blocking, mood, expression... Third, text-to-speach has come a long way, but it isn't there yet. It will be, and probably sooner than you think. The ones leading the charge aren't the movie companies, but the people who do call trees. The more realism and greater ease of change of message makes for a better and more competitive product for them. Movie people can still hire starving actors for voices for much less than the research into realistic text-to-speech. Well known actors often work at scale in animated movies too, just for the experience and free advertising they get. Finally, the best movie style to try this with is the old 1940's and 50's film noir. No special effects, no color, and dramatic but static lighting. Not so much an action picture, but more a mood and emotion picture (read "chick-flick" drama). "Sin City" was close, but I think something like "Dark Victory" or a good Sam Spade movie would be better.


gagnonrich ( ) posted Tue, 21 June 2005 at 5:36 PM

Let's not forget the skills required to use the tools effectively. What's the percentage of Poser users that can produce a photorealistic image with the program? Generally, the fault I see with most images is that the poses look wrong. Bodies are bent the wrong way or don't look properly balanced. Even if technology could drop prices to an affordable range to produce movies with 3D humans indistinguishable from real actors, it will be a rare individual that can actually seamlessly blend real and 3D togther. I'm not going to get into an argument over what is and isn't possible in 5-7 years. Personally, I don't see it happening that soon. I've yet to see a Hollywood movie, costing a hundred million dollars, that seamlessly did the job. Gollum was good, but the character was exaggerated enough that a lot of flaws were readily forgiven. I'd like to see a Hollywood budgeted film with a leading CG man or woman seamlessly interacting with other live actors before I start anticipating doing something similar all by my lonesome on a new super duper laptop. Having bought a new laptop five years after my previous, I can safely say that there wasn't a quantum leap in speed and capabilities in that timeframe. The new one is clearly faster the old one, but I haven't seen anything yet that has amazed me. I'm not ready to believe that my next laptop will be all that astonishing.

My visual indexes of Poser content are at http://www.sharecg.com/pf/rgagnon


jjsemp ( ) posted Tue, 21 June 2005 at 5:44 PM

Bill Hanna and Joe Barbera built an entire multi-million dollar cartoon empire on badly drawn and animated characters. And everybody already knew what good animation was, since Disney was in its prime when they did it. This is the Hollywood movie industry we're talking about. The fact is, you don't have to be all that good to be successful. You don't have to "seamlessly" do anything to make a success. And that Gollum flick? Didn't it win an Academy Award and make a bazillion dollars? -jjsemp


Nance ( ) posted Tue, 21 June 2005 at 6:52 PM

I would suggest that the real path will be a synthesis of live action and CGI. MoCap sequences performed by celebs to capture the nuances of their skill and performances, but the directors would then be able to modify and play what if in post to further enhance and manipulate the original performances. To master all of the individual crafts required to generate a masterful film would take multiple lifetimes to learn. Remember, even if a young Spielberg had all the techno toys he could imagine, Im certain hed be the first to admit that hes still not the skilled performer.


gagnonrich ( ) posted Tue, 21 June 2005 at 10:19 PM

After reading Spielberg's quote again, a lot of us misread what was said. He's talking about this capability being available to Hollywood in 5-7 years with a consumer capability happening sometime after that. That's more realistic, but I'll still have to see it to believe it. For it to happen in a fashion that can be sustained, the human figure would have to have a high degree of artificial intelligence to take the workload away from the animator to craft every single human nuance into the character. Technically, the realism can probably be achieved in the timeframe predicted. I'm less convinced that the artistic capability is there "to create a fully digital human being that would interface with other human beings and would be undetectable." Hey, if technology is so good that I can't tell which actor is real and which is digital, maybe I'll finally get that flying car and that will be way cooler!

My visual indexes of Poser content are at http://www.sharecg.com/pf/rgagnon


kennect ( ) posted Tue, 21 June 2005 at 11:38 PM

So does this idea mean that the director would also be considered the CG actors created? Who wins the Academy Award?


Keith ( ) posted Wed, 22 June 2005 at 2:48 AM

MoCap sequences performed by celebs to capture the nuances of their skill and performances, but the directors would then be able to modify and play what if in post to further enhance and manipulate the original performances. "Polar Express" did just that. Tom Hanks played multiple roles, including the kid, with the computer altering his appearance as required.



ScottA ( ) posted Wed, 22 June 2005 at 8:56 AM

Nuh UH gagnonrich..... George Lucas told jjsemp that we're all going to making full feature fims in our living rooms in about 5 years. I can't decide which film I'm going to make first. Maybe I'll re-make Gone with the wind. ;-)


lmckenzie ( ) posted Thu, 23 June 2005 at 2:55 AM

Criswell Predicts: There are already online render farms that you can send files to. By then, every business will be selling spare CPU cycles to the global grid and you will be able to rent vast amounts of horsepower to render your masterpiece. It should be possible using AI to create at least rudimentary digital assistants to help with lighting photography etc. There will be lots of kinky porn created, assuming the new theocracy hasn't outlawed it entirely by then. There will be a tremendous controversy over whether Vicki XXIV doing Mildog XVI should be legal. A raft of ultra-real videos depicting public figures engaged in illicit acts will cause the ultimate collapse of organized society as we know it. Bill Gates will become world emperor. Aliens from Epsilon Eridani, alarmed at mankind's primitive and violent nature will disable all technology. People will begin to draw kinky porn on the walls of their caves.

"Democracy is a pathetic belief in the collective wisdom of individual ignorance." - H. L. Mencken


maxxxmodelz ( ) posted Thu, 23 June 2005 at 9:16 AM

"There will be a tremendous controversy over whether Vicki XXIV doing Mildog XVI should be legal" LMAO! No doubt.


Tools :  3dsmax 2015, Daz Studio 4.6, PoserPro 2012, Blender v2.74

System: Pentium QuadCore i7, under Win 8, GeForce GTX 780 / 2GB GPU.


Privacy Notice

This site uses cookies to deliver the best experience. Our own cookies make user accounts and other features possible. Third-party cookies are used to display relevant ads and to analyze how Renderosity is used. By using our site, you acknowledge that you have read and understood our Terms of Service, including our Cookie Policy and our Privacy Policy.